HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Peng, Liu, Jiacheng, Hou, Xiaofeng, Pu, Yifei, Wang, Jing, Heng, Pheng-Ann, Li, Chao, Guo, Minyi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!